mparje / whisper-gpt3-streamlit

Whisper in combination with GPT-3

Whisper in combination with GPT-3 and Streamlit

upload a audio file to generate a transcript and then use GPT-3 to classify the transcripts sentiment.

Installation:

• Simply run the command pip install -r requirements.txt to install the necessary dependencies.

Usage:

1. Head over to this link and follow the steps to get a comprehensive overview of the architecture of OpenAI's whisper models.
2. Simply run the command:

streamlit run app.py

3. Navigate to http://localhost:8501 in your web-browser.
4. By default, streamlit allows us to upload files of max. 200MB. If you want to have more size for uploading audio files, execute the command :

streamlit run app.py --server.maxUploadSize=1028

How to start from here?:

Create a .env file in the root of the project and add your OpenAI GPT3 Key like this: OPENAI_API_KEY="sk-4xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx5"

Go to this line in app.py. Here you can modify the prompt to your needs. You can use the OpenAI Playground to test these first here

---

Join the LabLab Discord

On lablab discord, we discuss this repo and many other topics related to artificial intelligence! Checkout upcoming Artificial Intelligence Hackathons Event